# US 10,307,141 B2 · Thermography-based breast cancer screening using a measure of symmetry > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,307,141 B2 - Document ID: US10307141B2 - Status: Granted - Kind: B2 - Application number: 15/636,718 - Filed: 2017-06-29 - Published: 2018-01-04 - Granted: 2019-06-04 - Earliest claimed: 2016-06-29 - Applicants: Niramai Health Analytix Pvt. Ltd. - Inventors: Krithika Venkataramani; Susmija Jabbireddy; Himanshu J. Madhu; Siva Teja Kakileti; Hadonahalli V. Ramprakash - Web page: https://patentgrep.com/patent/US10307141B2 ## CPC - A61B 10/0041: {Detection of breast cancer (mammography by transillumination A61B5/0091, by X-rays A61B6/502, by ultrasonic means A61B8/0825)} - A61B 5/0033: {Features or image-related aspects of imaging apparatus, e.g. for MRI, optical tomography or impedance tomography apparatus; Arrangements of imaging apparatus in a room} - A61B 5/015: {By temperature mapping of body part} - A61B 5/4312: {Breast evaluation or disorder diagnosis (optical mammography A61B5/0091)} - G06T 7/0014: {using an image reference approach} - G06T 7/68: of symmetry - A61B 5/0013: {Medical image data (A61B1/00011, A61B6/56, A61B8/56 take precedence)} - A61B 2562/0276: comprising a thermosensitive compound - A61B 2576/02: specially adapted for a particular organ or body part - G06T 2207/10048: Infrared image - G06T 2207/30068: Mammography; Breast - G16H 30/40: for processing medical images, e.g. editing - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract What is disclosed is a system and method for breast cancer screening which determines whether hot spots, as seen in a thermal image of both breasts, can be classified as possibly malignant based on a measure of symmetry. A thermographic image of both breasts of a patient is received and analyzed to determine whether there exists, in each of a left breast and a right breast, a hot spot comprising a patch of pixels with an elevated temperature with respect to surrounding tissue. If a hot spot has been identified in each breast then a measure of symmetry comprising a ratio of an area of a smaller hot spot to an area of a larger hot spot is extracted from the thermographic image. The measure of symmetry is provided to a classifier system trained to classify an unclassified hot spot as malignant or non-malignant based on a measure of symmetry. ## Claims ### Claim 1 A method for breast cancer screening using a measure of symmetry extracted from a thermographic image of a left and right breast of a patient, the method comprising: receiving at least one thermographic image of a left and right breast of a patient; analyzing the thermographic image to determine whether a hot spot exists in each of a left breast and a right breast, a hot spot comprising a patch of pixels with an elevated temperature with respect to a temperature of pixels in surrounding tissue; and in response to a hot spot being identified in each breast, performing: extracting a measure of symmetry, wherein said extracting the measure of symmetry comprises binarizing the hot spots in each breast, with a value of 1 for pixels in the hot spots and a value of 0 for other pixels; convoluting the binary maps of the two breasts; and using a maximum value in the convolution as a measure of overlap area between the hot spots of the left and right breasts; and providing the overlap area as a measure of symmetry to a classifier system trained to classify an unclassified hot spot as being possibly malignant and non-malignant otherwise, based on a measure of symmetry. ### Claim 2 (depends on 1) The method of claim 1, wherein the hot spot inclusion of a given patch of pixels is based on one of: a mean temperature of pixels in the patch, a median temperature of pixels in the patch, and a highest temperature of pixels in the patch. ### Claim 3 (depends on 1) The method of claim 1, wherein, in response to more than one hot spot being identified in either the left or right breast, further comprising selecting one of the hot spots for malignancy analysis and reporting. ### Claim 4 (depends on 3) The method of claim 3, wherein in addition to the hot spot, one or more warm spots are identified as potential abnormal elements that require attention, wherein the potential abnormal elements comprise information for classifying the hot spot as possibly malignant. ### Claim 5 (depends on 1) The method of claim 1, wherein, in response to a hot spot being classified as possibly malignant or non-malignant, further comprising initiating an alert or a diagnostic report comprising any of: an audio message, a sound, a text message, sending an email, sending a text message, placing a phone call, playing a video, blinking a light, and wirelessly activating a remote device. ### Claim 6 (depends on 1) The method of claim 1, wherein the classifier system comprises any of: Support Vector Machine, a neural network, a Bayesian network, a Logistic regression, Naive Bayes, Randomized Forests, Decision Trees and Boosted Decision Trees, K-nearest neighbor, a Restricted Boltzmann Machine, and a hybrid system comprising any combination hereof. ### Claim 7 (depends on 1) The method of claim 1, further comprising updating a training set used to train the classifier system and improve the classifier system for classifying the hot spot. ### Claim 8 (depends on 1) The method of claim 1, further comprising communicating the classification to any of: a storage device, a display device, and a remote device over a network. ### Claim 9 (depends on 1) The method of claim 1, where the convolution is done with the temperature maps of the hot-spots of each breast with the rest of the pixels set to zero. ### Claim 10 (depends on 1) The method of claim 1, wherein said extracting the measure of symmetry further comprises binarizing the hot-spots in each breast, with a value of 1 for pixels in the hot spots and a value of 0 for other pixels; computing the area of hotspots as the number of pixels with a value of 1, separately for the left breast and right breast; determining the ratio of smaller hot spot area of one breast to the larger hot spot area in a contralateral breast; and providing the ratio of the areas as a measure of symmetry to a classifier system trained to classify an unclassified hot spot as being possibly malignant and non-malignant otherwise, based on the measure of symmetry. ### Claim 11 A system for breast cancer screening using a measure of symmetry extracted from a thermographic image of a left and right breast of a patient, the system comprising: a storage device; and a processor in communication with the storage device, the processor retrieving executing machine readable program instructions which, when executed by the processor, enable the processor to: receive at least one thermographic image of a left and right breast of a patient; analyze the thermographic image to determine whether a hot spot exists in each of a left breast and a right breast, a hot spot comprising a patch of pixels with an elevated temperature with respect to a temperature of pixels in surrounding tissue; and in response to a hot spot being identified in each breast, performing: extract a measure of symmetry, wherein said extraction of the measure of symmetry comprises binarizing the hot-spots in each breast, with a value of 1 for pixels in the hot spots and a value of 0 for other pixels; convoluting the binary maps of the two breasts; and using a maximum value in the convolution as a measure of overlap area between the hot spots of the left and right breasts; and provide the overlap area as a measure of symmetry to a classifier system trained to classify an unclassified hot spot as being possibly malignant and non-malignant otherwise, based on a measure of symmetry. ### Claim 12 (depends on 11) The system of claim 11, wherein the hot spot inclusion of a given patch of pixels is based on one of: a mean temperature of pixels in the patch, a median temperature of pixels in the patch, and a highest temperature of pixels in the patch. ### Claim 13 (depends on 11) The system of claim 11, wherein, in response to more than one hot spot being identified in either the left or right breast, the processor further being configured to select one of the hot spots for malignancy analysis and reporting. ### Claim 14 (depends on 13) The system of claim 13, wherein in addition to the hot spot, one or more warm spots are identified as potential abnormal elements that require attention, wherein the potential abnormal elements comprise information for classifying the hot spot as possibly malignant. ### Claim 15 (depends on 11) The system of claim 11, wherein, in response to a hot spot being classified as possibly malignant or non-malignant, the processor further configured to initiate an alert or a diagnostic report comprising any of: an audio message, a sound, a text message, sending an email, sending a text message, placing a phone call, playing a video, blinking a light, and wirelessly activating a remote device. ### Claim 16 (depends on 11) The system of claim 11, wherein the classifier system comprises any of: Support Vector Machine, a neural network, a Bayesian network, a Logistic regression, Naïve Bayes, Randomized Forests, Decision Trees and Boosted Decision Trees, K-nearest neighbor, a Restricted Boltzmann Machine, and a hybrid system comprising any combination hereof. ### Claim 17 (depends on 11) The system of claim 11, wherein the processor is further configured to update a training set used to train the classifier system and to improve the classifier system for classifying the hot spot. ### Claim 18 (depends on 11) The system of claim 11, wherein the processor is further configured to communicate the classification to any of: a storage device, a display device, and a remote device over a network. ### Claim 19 A method for breast cancer screening using a measure of symmetry extracted from a thermographic image of a left and right breast of a patient, the method comprising: receiving at least one thermographic image of a left and right breast of a patient; analyzing the thermographic image to determine whether a hot spot exists in each of a left breast and a right breast, a hot spot comprising a patch of pixels with an elevated temperature with respect to a temperature of pixels in surrounding tissue; and in response to a hot spot being identified in each breast, performing: extracting a measure of symmetry, wherein said extracting the measure of symmetry comprises binarizing the hot-spots in each breast, with a value of 1 for pixels in the hot spots and a value of 0 for other pixels; computing the area of hotspots as the number of pixels with a value of 1, separately for the left breast and right breast; and determining the ratio of smaller hot spot area of one breast to the larger hot spot area in a contralateral breast; and providing the ratio of the areas as a measure of symmetry to a classifier system trained to classify an unclassified hot spot as being possibly malignant and non-malignant otherwise, based on the measure of symmetry.